Insightful Assistant: AI-compatible Operation Graph Representations for Enhancing Industrial Conversational Agents

TL;DR

This paper introduces Insightful Assistant, a novel operation graph framework for industrial conversational agents that integrates AI operations, enabling more complex, accurate, and user-adaptive interactions in industrial settings.

Contribution

It proposes a new operation graph representation for industrial assistants, combining AI functions with user preferences, and demonstrates its effectiveness on a large, annotated industrial request dataset.

Findings

Achieves up to 95.0% accuracy in simple request detection

Reaches 74.5% accuracy for complex requests

Top-3 visualization accuracy up to 95.4%

Abstract

Advances in voice-controlled assistants paved the way into the consumer market. For professional or industrial use, the capabilities of such assistants are too limited or too time-consuming to implement due to the higher complexity of data, possible AI-based operations, and requests. In the light of these deficits, this paper presents Insightful Assistant---a pipeline concept based on a novel operation graph representation resulting from the intents detected. Using a predefined set of semantically annotated (executable) functions, each node of the operation graph is assigned to a function for execution. Besides basic operations, such functions can contain artificial intelligence (AI) based operations (e.g., anomaly detection). The result is then visualized to the user according to type and extracted user preferences in an automated way. We further collected a unique crowd-sourced set of 869 requests, each with four different variants expected visualization, for an industrial dataset. The evaluation of our proof-of-concept prototype on this dataset shows its feasibility: it achieves an accuracy of up to 95.0% (74.5%) for simple (complex) request detection with different variants and a top3-accuracy up to 95.4% for data-/user-adaptive visualization.